Overview
This course focuses on Zero-Change Object Transmission for Distributed Big Data Analytics. The learning outcomes include understanding the challenges of data exchange in distributed big-data analytics, learning about the concept and benefits of Zero-Change Object Transmission (ZCOT), and exploring how ZCOT can improve application performance. The course teaches skills such as analyzing the workflow of big-data processing, optimizing inter-JVM communications, implementing ZCOT, and evaluating its impact on performance. The teaching method includes lectures on the challenges, benefits, and implementation of ZCOT, as well as practical sessions on experimental setups and performance evaluations. The intended audience for this course includes data engineers, software developers, and professionals working in distributed big-data analytics who are interested in optimizing data exchange processes for improved performance.
Syllabus
Intro
Distributed Big-data Analytics
Workflow of Big-data Processing
Costly Inter-JVM Communications
Existing S/D Optimizations
How to Achieve This?
Challenges for ZCOT
Space Construction: DCDS
Compatibility with Applications
Distributed Memory Management
RPC Interfaces
The Workflow of ZCOT
Experimental Setup
Mircobenchmark
Flink Performance
Conclusion
Taught by
USENIX